© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31643
    Prev
    Next
    INDEX
    Explanations

    skills reviewed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansen
    -0.08
    ë²Į
    -0.08
    dor
    -0.07
    èĥľ
    -0.07
    üz
    -0.07
    rah
    -0.06
     coma
    -0.06
    fl
    -0.06
    age
    -0.06
     Beaver
    -0.06
    POSITIVE LOGITS
    ç´Ģ
    0.08
    erci
    0.08
    онеÑĢ
    0.07
    á»ĵn
    0.07
    ibar
    0.07
    æĹ¥æĸ°æľĪ
    0.07
    ARGE
    0.07
    нÑĥÑĤ
    0.07
    妥å½ĵ
    0.07
    ׾×ij
    0.07
    Activations Density 0.013%

    No Known Activations